Optimization of Stacking Ensemble Models for Decision Support Systems Based on Multidimensional Population Demographics
Authors
Ibragimov Mukhiddin Fakhraddin ugli, Jumanazarov Azizbek Dilshodovich, Mashiripov Behruzbek Gayrat ugli, Zarifboyev Javohir Dilshod ugli, Umarova Mukhlisa Khushnudbek qizi
Share
Annotation
Currently, significant efforts are being directed toward improving the socio-economic status of the population and digitizing the activities of local neighborhood (mahalla) institutions. In this context, the integration of machine learning methods with demographic data provides an opportunity to develop intelligent decision support systems for local executive authorities. Given that individual machine learning algorithms often encounter limitations when training on complex demographic indicators, this study implements optimization through stacking ensemble techniques. Based on nine primary parameters, XGBoost, regression algorithms, and Artificial Neural Networks (ANN) were selected as base learners and integrated into a stacking ensemble framework. The methodology involved preprocessing the database, constructing the ensemble model, and utilizing Ridge Regression as the meta-learner, with model parameters optimized via cross-validation. Experimental results demonstrate that the stacking ensemble model significantly outperforms standalone models in terms of predictive accuracy and robustness. Specifically, the stacking ensemble achieved a 36.9% improvement in performance compared to the standalone XGBoost model. This approach ensures high-precision forecasting of demographic indicators, providing a reliable foundation for decision support systems within executive government agencies.
Keywords
Authors
Ibragimov Mukhiddin Fakhraddin ugli, Jumanazarov Azizbek Dilshodovich, Mashiripov Behruzbek Gayrat ugli, Zarifboyev Javohir Dilshod ugli, Umarova Mukhlisa Khushnudbek qizi
Share
References:
Yusupov F. X. X. X., Ibragimov M. F., Babayazov S. P. Prediction of Interactions Between Social Groups and Decision-Making Using Fuzzy Models //2024 IEEE 3rd International Conference on Problems of Informatics, Electronics and Radio Engineering (PIERE). – IEEE, 2024. – С. 1520-1523.
Yusupov F. X. X. X. et al. Improving the Computing Accuracy of the AI Ascend Processor: Research and Results //2024 IEEE 3rd International Conference on Problems of Informatics, Electronics and Radio Engineering (PIERE). – IEEE, 2024. – С. 1510-1513.
M. F. Ibragimov, O. K. Khujaev and K. J. Rakhimboev, "Development of a Module for Evaluating the Activity of the Mahalla Chairpersons Based on the Experts' Assessment with the Help of Machine Learning Algorithms," 2023 IEEE XVI International Scientific and Technical Conference Actual Problems of Electronic Instrument Engineering (APEIE), Novosibirsk, Russian Federation, 2023, pp. 1730-1733, doi: 10.1109/APEIE59731.2023.10347584.
M. Ibragimov, B. Babajanov, S. Sapayev, M. Otaboyeva, O. Aliev and S. Rakhimberdiev, "Scientifically Grounded Model for Managing and Evaluating Community Health-Promotion Activities at the Mahalla Level," 2025 IEEE XVII International Scientific and Technical Conference on Actual Problems of Electronic Instrument Engineering (APEIE), Novosibirsk, Russian Federation, 2025, pp. 1-6, doi: 10.1109/APEIE66761.2025.11289459.
Ali, T. E. A Stacking Ensemble Model with Enhanced Feature Selection for Distributed Denial-of-Service Detection in Software-Defined Networks / T. E. Ali, Y. W. Chong, S. Manickam [et al.] // Engineering, Technology & Applied Science Research. – 2025. – Vol. 15. – No. 1. – P. 19232–19245.
Lu, M. A Stacking Ensemble Model of Various Machine Learning Models for Daily Runoff Forecasting / M. Lu, Q. Hou, S. Qin [et al.] // Water. – 2023. – Vol. 15. – No. 7. – Art. 1265.
Divina, F. Stacking Ensemble Learning for Short-Term Electricity Consumption Forecasting / F. Divina, A. Gilson, F. Goméz-Vela [et al.] // Energies. – 2018. – Vol. 11. – No. 9. – Art. 949.
Yao, J. Applications of Stacking/Blending ensemble learning approaches for evaluating flash flood susceptibility / J. Yao, X. Zhang, W. Luo [et al.] // International Journal of Applied Earth Observation and Geoinformation. – 2022. – Vol. 112. – Art. 102932.
Zhao, S. Stacking Ensemble Learning-Based [18F]FDG PET Radiomics for Outcome Prediction in Diffuse Large B-Cell Lymphoma / S. Zhao, J. Wang, C. Jin [et al.] // Journal of Nuclear Medicine. – 2023. – DOI: 10.2967/jnumed.122.265244.
Obaidat, M. A. Machine Learning Stacking Ensemble Model for Predicting Heart Attacks / M. A. Obaidat, A. Alexandrou, S. Sanacore // ALLDATA 2022: The Eighth International Conference on Big Data, Small Data, Linked Data and Open Data. – 2022.
Golder, K. An Empirical Study on Developing Stacking Ensemble Model for Bangla Sports Sentiment Analysis / K. Golder, P. Biswas, M. S. Islam [et al.] // 15th International Conference on Computing Communication and Networking Technologies (ICCCNT). – 2024.
Other articles of the issue
